Pub Date : 2016-12-01DOI: 10.1109/ICIAFS.2016.7946547
Sriendra Deshan Ilangakoon, J. Jayakody
This research work presents new trends in cyber threats, and it also quantifies user awareness of web threats and attacks. Using an online questionnaire information for the analysis of whether individuals had adequate knowledge of internet threats and attacks in order to safeguard themselves was obtained. The survey showed that many users lack an adequate understanding of what to do and what not to do in order to remain safe on the internet. Therefore, it is crucial that training and awareness be given to all individuals, especially at a young age.
{"title":"Awareness of Sri Lankan internet users on web browsing related threats and vulnerabilities","authors":"Sriendra Deshan Ilangakoon, J. Jayakody","doi":"10.1109/ICIAFS.2016.7946547","DOIUrl":"https://doi.org/10.1109/ICIAFS.2016.7946547","url":null,"abstract":"This research work presents new trends in cyber threats, and it also quantifies user awareness of web threats and attacks. Using an online questionnaire information for the analysis of whether individuals had adequate knowledge of internet threats and attacks in order to safeguard themselves was obtained. The survey showed that many users lack an adequate understanding of what to do and what not to do in order to remain safe on the internet. Therefore, it is crucial that training and awareness be given to all individuals, especially at a young age.","PeriodicalId":237290,"journal":{"name":"2016 IEEE International Conference on Information and Automation for Sustainability (ICIAfS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129682653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-01DOI: 10.1109/ICIAFS.2016.7946574
H. Afrisal, S. Sadati, T. Nanayakkara
Smart attachment mechanisms are believed to contribute significantly in stiffness control of soft robots. This paper presents a working prototype of an active Velcro based stiffness controllable fastening mechanism inspired from micro active hooks found in some species of plants and animals. In contrast to conventional passive Velcro, this active Velcro mechanism can vary the stiffness level of its hooks to adapt to external forces and to maintain the structure of its supported layer. The active hooks are fabricated using Shape Memory Alloy (SMA) wires which can be actuated using Lenz-Joule heating technique via thermo-electric manipulation. In this paper, we show experimental results for the effects of active SMA Velcro temperature, density and number on the attachment resisting force profile in dynamic displacement. We aim to provide new insights into the novel design approach of using active hook systems to support future implementation of active velcro mechanisms for fabrication of wearable stiffness controllable thin layers.
{"title":"A bio-inspired electro-active Velcro mechanism using Shape Memory Alloy for wearable and stiffness controllable layers","authors":"H. Afrisal, S. Sadati, T. Nanayakkara","doi":"10.1109/ICIAFS.2016.7946574","DOIUrl":"https://doi.org/10.1109/ICIAFS.2016.7946574","url":null,"abstract":"Smart attachment mechanisms are believed to contribute significantly in stiffness control of soft robots. This paper presents a working prototype of an active Velcro based stiffness controllable fastening mechanism inspired from micro active hooks found in some species of plants and animals. In contrast to conventional passive Velcro, this active Velcro mechanism can vary the stiffness level of its hooks to adapt to external forces and to maintain the structure of its supported layer. The active hooks are fabricated using Shape Memory Alloy (SMA) wires which can be actuated using Lenz-Joule heating technique via thermo-electric manipulation. In this paper, we show experimental results for the effects of active SMA Velcro temperature, density and number on the attachment resisting force profile in dynamic displacement. We aim to provide new insights into the novel design approach of using active hook systems to support future implementation of active velcro mechanisms for fabrication of wearable stiffness controllable thin layers.","PeriodicalId":237290,"journal":{"name":"2016 IEEE International Conference on Information and Automation for Sustainability (ICIAfS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129709483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-01DOI: 10.1109/ICIAFS.2016.7946562
Sasika Roledene, Lakna Ariyathilaka, N. Liyanage, P. Lakmal, J. Bamunusinghe
The Foreign Currency Exchange market (Forex) is the largest financial market in the world with the highest daily trading volume. A highly volatile complex behavior is seen during the time the market is open and understanding market trend patterns solves an enormous amount of problems pertaining to prediction and decision making. Many often traders write trading strategies to identify the significant patterns they have recognized. This concept directly involves trading automation or algorithmic trading but building such a versatile algorithm is quite challenging unless you have a person to suggest improvements in your own algorithm. Therefore, in this paper we propose an intelligent system called Genibux will assist Forex traders to improve their strategies. The system suggests improvements with justifications for the maximum gain of profit. Genibux is mainly based on Complex Event Processing and it has been implemented with highly comprehensible Genibux Strategy Language (GSL) together with Machine Learning and classifying algorithms enclosed in a set of highly interactive interfaces. Most importantly, it performs exceedingly well and depicts more profit gains through Genibux improved trading strategies.
{"title":"GeniBux - event based intelligent Forex trading strategy enhancer","authors":"Sasika Roledene, Lakna Ariyathilaka, N. Liyanage, P. Lakmal, J. Bamunusinghe","doi":"10.1109/ICIAFS.2016.7946562","DOIUrl":"https://doi.org/10.1109/ICIAFS.2016.7946562","url":null,"abstract":"The Foreign Currency Exchange market (Forex) is the largest financial market in the world with the highest daily trading volume. A highly volatile complex behavior is seen during the time the market is open and understanding market trend patterns solves an enormous amount of problems pertaining to prediction and decision making. Many often traders write trading strategies to identify the significant patterns they have recognized. This concept directly involves trading automation or algorithmic trading but building such a versatile algorithm is quite challenging unless you have a person to suggest improvements in your own algorithm. Therefore, in this paper we propose an intelligent system called Genibux will assist Forex traders to improve their strategies. The system suggests improvements with justifications for the maximum gain of profit. Genibux is mainly based on Complex Event Processing and it has been implemented with highly comprehensible Genibux Strategy Language (GSL) together with Machine Learning and classifying algorithms enclosed in a set of highly interactive interfaces. Most importantly, it performs exceedingly well and depicts more profit gains through Genibux improved trading strategies.","PeriodicalId":237290,"journal":{"name":"2016 IEEE International Conference on Information and Automation for Sustainability (ICIAfS)","volume":"165 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127983629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-01DOI: 10.1109/ICIAFS.2016.7946542
Josefa Wivou, L. Udawatta, Ali Alshehhi, Ebrahim Alzaabi, Ahmed Albeloshi, Saeed Alfalasi
We propose a novel system that collects air sampling field data for a given location in 3D space. A drone mounted with relevant components for air quality measuring is deployed. Data collected from the system will be efficiently transmitted to the storing and monitoring devices. Knowledge of existing air pollutants levels and patterns are taken into consideration in order to analyse a given situation. Data will be stored in cloud storage for further analysis and record keeping. Results show the effectiveness of the proposed methodology.
{"title":"Air quality monitoring for sustainable systems via drone based technology","authors":"Josefa Wivou, L. Udawatta, Ali Alshehhi, Ebrahim Alzaabi, Ahmed Albeloshi, Saeed Alfalasi","doi":"10.1109/ICIAFS.2016.7946542","DOIUrl":"https://doi.org/10.1109/ICIAFS.2016.7946542","url":null,"abstract":"We propose a novel system that collects air sampling field data for a given location in 3D space. A drone mounted with relevant components for air quality measuring is deployed. Data collected from the system will be efficiently transmitted to the storing and monitoring devices. Knowledge of existing air pollutants levels and patterns are taken into consideration in order to analyse a given situation. Data will be stored in cloud storage for further analysis and record keeping. Results show the effectiveness of the proposed methodology.","PeriodicalId":237290,"journal":{"name":"2016 IEEE International Conference on Information and Automation for Sustainability (ICIAfS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121150492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-01DOI: 10.1109/ICIAFS.2016.7946552
D. D. De Silva, I. Kaluthanthri, K. S. Sudaraka, U. P. D. Karunarathna, J. Jayalath
Over the decades, travelling has experienced continuous growth and deepening diversification to become one of the fastest growing economic sectors in the world. Among the existing travelling applications, only a handful facilitate the ability to plan a tour which is entirely based on user preferences, while offering an in-depth look at the desired destination. Therefore, this research focuses on integrating semantic technologies, collaborative filtering and Virtual Reality into the domain of travelling and provide preferred user oriented tour plans with superlative user satisfaction. The key factor that needs to be understood is that the preferences or the behavior of one user may be entirely different from another. “Scylax” has introduced the concept of preferences and behavior based personalized tour planning and the way of exploring desired routes, major stops or attractions along the way via virtual reality 360 view experience. In addition, business organizations can use the web-based dashboard to maintain their services, offers and obtain business analytic based improvements.
{"title":"Scylax - preference based personalized Tour Planner with Virtual Reality","authors":"D. D. De Silva, I. Kaluthanthri, K. S. Sudaraka, U. P. D. Karunarathna, J. Jayalath","doi":"10.1109/ICIAFS.2016.7946552","DOIUrl":"https://doi.org/10.1109/ICIAFS.2016.7946552","url":null,"abstract":"Over the decades, travelling has experienced continuous growth and deepening diversification to become one of the fastest growing economic sectors in the world. Among the existing travelling applications, only a handful facilitate the ability to plan a tour which is entirely based on user preferences, while offering an in-depth look at the desired destination. Therefore, this research focuses on integrating semantic technologies, collaborative filtering and Virtual Reality into the domain of travelling and provide preferred user oriented tour plans with superlative user satisfaction. The key factor that needs to be understood is that the preferences or the behavior of one user may be entirely different from another. “Scylax” has introduced the concept of preferences and behavior based personalized tour planning and the way of exploring desired routes, major stops or attractions along the way via virtual reality 360 view experience. In addition, business organizations can use the web-based dashboard to maintain their services, offers and obtain business analytic based improvements.","PeriodicalId":237290,"journal":{"name":"2016 IEEE International Conference on Information and Automation for Sustainability (ICIAfS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121835010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-01DOI: 10.1109/ICIAFS.2016.7946545
V. T. N. Vidanagama
Advances in technology have enabled wireless devices to monitor and provide information than ever before. These sensors/actuators can be incorporated into any device to provide the user an immersive experience which include services such as connected-consumer, e-Health and smart transportation etc. Bluetooth Smart has emerged as popular wireless communication technology for such devices. The Received Signal Strength Indicator (RSSI) has been used as an indicator to manage connections between Bluetooth smart devices. However the instability of real world radio signals causes variations in the RSSI value. This paper investigates the severity of this phenomenon in the European Telecommunications Standards Institute (ETSI) Machine-to-Machine (M2M) device and gateway domain.
{"title":"Effect of signal variation on M2M gateway selection for short range wireless devices","authors":"V. T. N. Vidanagama","doi":"10.1109/ICIAFS.2016.7946545","DOIUrl":"https://doi.org/10.1109/ICIAFS.2016.7946545","url":null,"abstract":"Advances in technology have enabled wireless devices to monitor and provide information than ever before. These sensors/actuators can be incorporated into any device to provide the user an immersive experience which include services such as connected-consumer, e-Health and smart transportation etc. Bluetooth Smart has emerged as popular wireless communication technology for such devices. The Received Signal Strength Indicator (RSSI) has been used as an indicator to manage connections between Bluetooth smart devices. However the instability of real world radio signals causes variations in the RSSI value. This paper investigates the severity of this phenomenon in the European Telecommunications Standards Institute (ETSI) Machine-to-Machine (M2M) device and gateway domain.","PeriodicalId":237290,"journal":{"name":"2016 IEEE International Conference on Information and Automation for Sustainability (ICIAfS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125334391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-01DOI: 10.1109/ICIAFS.2016.7946531
Malin Prematilake, Buddhi Wickramasinghe, Olitha Vithanage, Hasindu Gamaarachchi, R. Ragel
Side Channel Attacks are a popular modern cryptanalysis technique used by adversaries in embedded devices to break the security key. In these types of attacks, the attackers are keen on identifying the weaknesses of the physical implementation of the cryptosystem and utilize such vulnerabilities to extract the key. Power Analysis Attack is a form of Side Channel Attack in which, the adversary exploits power consumed by a cryptographic device during encryption to obtain the key. Mutual Information Analysis (MIA) is a concept introduced in information theory that measures the dependence between two random variables. In MIA based Power Analysis Attack, mutual information between two random variables is taken as the side channel distinguisher. Here, the two variables are physical leakages of the device and the power model based on key estimates. Since this method has more advantages to attackers compared to other methods, it is vital for cryptanalysts to find better countermeasures against this. But, due to the lack of efficient implementations it is hard for cryptanalysts to do that kind of research. In this paper, we present a methodology to accelerate MIA based Power Analysis Attacks using a GPU (Graphical Processor Unit) like NVIDIA Compute Unified Device Architecture (CUDA). Our proposed method promises to better utilize the capabilities of NVIDIA CUDA and obtain a speedup of more than 100 times compared to its sequential version.
{"title":"Accelerating Mutual Information Analysis based Power Analysis Attacks Using GPU","authors":"Malin Prematilake, Buddhi Wickramasinghe, Olitha Vithanage, Hasindu Gamaarachchi, R. Ragel","doi":"10.1109/ICIAFS.2016.7946531","DOIUrl":"https://doi.org/10.1109/ICIAFS.2016.7946531","url":null,"abstract":"Side Channel Attacks are a popular modern cryptanalysis technique used by adversaries in embedded devices to break the security key. In these types of attacks, the attackers are keen on identifying the weaknesses of the physical implementation of the cryptosystem and utilize such vulnerabilities to extract the key. Power Analysis Attack is a form of Side Channel Attack in which, the adversary exploits power consumed by a cryptographic device during encryption to obtain the key. Mutual Information Analysis (MIA) is a concept introduced in information theory that measures the dependence between two random variables. In MIA based Power Analysis Attack, mutual information between two random variables is taken as the side channel distinguisher. Here, the two variables are physical leakages of the device and the power model based on key estimates. Since this method has more advantages to attackers compared to other methods, it is vital for cryptanalysts to find better countermeasures against this. But, due to the lack of efficient implementations it is hard for cryptanalysts to do that kind of research. In this paper, we present a methodology to accelerate MIA based Power Analysis Attacks using a GPU (Graphical Processor Unit) like NVIDIA Compute Unified Device Architecture (CUDA). Our proposed method promises to better utilize the capabilities of NVIDIA CUDA and obtain a speedup of more than 100 times compared to its sequential version.","PeriodicalId":237290,"journal":{"name":"2016 IEEE International Conference on Information and Automation for Sustainability (ICIAfS)","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121766160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-01DOI: 10.1109/ICIAFS.2016.7946572
D. D. De Silva, S. Saleem, J. A. Mariathas, T. Veerasingham, S. Mahawithana
Images are the only source where the user can capture the real world environment on a two dimensional space. But these days the user has to use many cropping and cloning tools to manipulate, remove and do all necessary editing to an object in digital images. Smart image is developed as revolutionary solution with simpler user interfaces for users to interact with these digital images. The system helps to extract the objects and reconstructs the background with minimal user interaction. The user simply has to select an object to manipulate or remove. The wall is detected with edge detection and the color and texture of the wall is changed according to the user input. In addition to those features there will be a mobile version for the proposed system to capture a set of images of objects of their interest are captured and the system generates a three dimensional model from the design item. The system is demonstrated on a range of real world images and validated.
{"title":"Smart image - interaction with digital image","authors":"D. D. De Silva, S. Saleem, J. A. Mariathas, T. Veerasingham, S. Mahawithana","doi":"10.1109/ICIAFS.2016.7946572","DOIUrl":"https://doi.org/10.1109/ICIAFS.2016.7946572","url":null,"abstract":"Images are the only source where the user can capture the real world environment on a two dimensional space. But these days the user has to use many cropping and cloning tools to manipulate, remove and do all necessary editing to an object in digital images. Smart image is developed as revolutionary solution with simpler user interfaces for users to interact with these digital images. The system helps to extract the objects and reconstructs the background with minimal user interaction. The user simply has to select an object to manipulate or remove. The wall is detected with edge detection and the color and texture of the wall is changed according to the user input. In addition to those features there will be a mobile version for the proposed system to capture a set of images of objects of their interest are captured and the system generates a three dimensional model from the design item. The system is demonstrated on a range of real world images and validated.","PeriodicalId":237290,"journal":{"name":"2016 IEEE International Conference on Information and Automation for Sustainability (ICIAfS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132682953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-01DOI: 10.1109/ICIAFS.2016.7946553
Chirath Pathiravasam, Ganesh K. Venayagamorthy
Integration of large-scale wind power plants to the power system is a challenge as the power generation is variable, and energy management systems require accurate prediction of wind power for a stable operation. Frequency control, economic dispatch and unit commitment problems in power system operations depend on forecasted wind power. Due to the dynamic changes in wind patterns, wind speed (and power) is very difficult to predict. In this paper, several computational approaches using neural networks (NN) for wind speed prediction is presented. Cellular Computational Networks (CCNs) are found to be more accurate than Multilayer Perceptrons (MLPs) and Recurrent Neural Networks (RNNs). This is due to capability of CCNs to simultaneously capture spatial-temporal characteristics of wind. The effectiveness of standard backpropagation, Backpropagation Through Time (BPTT) algorithm and Particle Swarm Optimization (PSO) are compared for training the computational networks. Performance of PSO algorithm is comparatively better than that of BPTT for training CCNs with MLPs.
{"title":"Spatio-temporal characteristics based wind speed predictions","authors":"Chirath Pathiravasam, Ganesh K. Venayagamorthy","doi":"10.1109/ICIAFS.2016.7946553","DOIUrl":"https://doi.org/10.1109/ICIAFS.2016.7946553","url":null,"abstract":"Integration of large-scale wind power plants to the power system is a challenge as the power generation is variable, and energy management systems require accurate prediction of wind power for a stable operation. Frequency control, economic dispatch and unit commitment problems in power system operations depend on forecasted wind power. Due to the dynamic changes in wind patterns, wind speed (and power) is very difficult to predict. In this paper, several computational approaches using neural networks (NN) for wind speed prediction is presented. Cellular Computational Networks (CCNs) are found to be more accurate than Multilayer Perceptrons (MLPs) and Recurrent Neural Networks (RNNs). This is due to capability of CCNs to simultaneously capture spatial-temporal characteristics of wind. The effectiveness of standard backpropagation, Backpropagation Through Time (BPTT) algorithm and Particle Swarm Optimization (PSO) are compared for training the computational networks. Performance of PSO algorithm is comparatively better than that of BPTT for training CCNs with MLPs.","PeriodicalId":237290,"journal":{"name":"2016 IEEE International Conference on Information and Automation for Sustainability (ICIAfS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133338882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-01DOI: 10.1109/ICIAFS.2016.7946563
H. Nagahamulla, U. Ratnayake, A. Ratnaweera
Artificial Neural Network (ANN) is a widely used technique in forecasting applications. An ensemble of ANNs can produce more accurate forecasts than a single ANN. The performance of the ensemble depends on its' member ANN. Member selection for an ensemble is a complicated task that need balancing conflicting conditions. This paper presents a method to optimize the selection of members for an ANN ensemble using Genetic Algorithms approach. To develop the models daily weather data are used. Rainfall data for Colombo, Sri Lanka are used to develop and test the models and rainfall data for Katugastota, Sri Lanka are used to validate the models. The results obtained are compared with two widely used member selection methods Bagging and Boosting. The ensemble model (ENN-GA) performed better than Bagging and Boosting methods and managed to produce forecasts with RMSE 7.30 for Colombo and RMSE 6.21 for Katugastota.
{"title":"Optimizing member selection for Neural Network ensembles using Genetic Algorithms","authors":"H. Nagahamulla, U. Ratnayake, A. Ratnaweera","doi":"10.1109/ICIAFS.2016.7946563","DOIUrl":"https://doi.org/10.1109/ICIAFS.2016.7946563","url":null,"abstract":"Artificial Neural Network (ANN) is a widely used technique in forecasting applications. An ensemble of ANNs can produce more accurate forecasts than a single ANN. The performance of the ensemble depends on its' member ANN. Member selection for an ensemble is a complicated task that need balancing conflicting conditions. This paper presents a method to optimize the selection of members for an ANN ensemble using Genetic Algorithms approach. To develop the models daily weather data are used. Rainfall data for Colombo, Sri Lanka are used to develop and test the models and rainfall data for Katugastota, Sri Lanka are used to validate the models. The results obtained are compared with two widely used member selection methods Bagging and Boosting. The ensemble model (ENN-GA) performed better than Bagging and Boosting methods and managed to produce forecasts with RMSE 7.30 for Colombo and RMSE 6.21 for Katugastota.","PeriodicalId":237290,"journal":{"name":"2016 IEEE International Conference on Information and Automation for Sustainability (ICIAfS)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116545505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：